Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dfcdb2eb191f1beddcea46e2ac9926a6c6e3ea6ac2eda4f6063febe7090e40
+oid sha256:d226a98cc4cf95e371c20b16ff17d84cd68a6bfd2993fa578a341f9d1ebffc86
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd576b2e5df85c2efee5156f3dcc874240875ec97cb286155ca205814be54b2
+oid sha256:1a18595d23f4c3bc47e6b090890adbd6e5e5e290f4e989acd426efa72bea6e41
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7ec423b1e2a3fc2ca790ddc4370fec88c8249a3964daf8a870d6f32dd37903
+oid sha256:c7290ba3a1aefb83c84bf56fe8edb02a6104be8b529a49f97407a9638b519106
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7cf500208b0b7f84d388a948be38cab3fa49ec9e5ed4521e775b2c1f3ef453
+oid sha256:debca7aba43b980bfea4b7bfb85075c00dd93d0ca0b163523a96099f24c727ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4784965515136719,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.05517748758506529,
+  "best_metric": 1.464486837387085,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.07356998344675372,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 17.56,
       "eval_steps_per_second": 4.402,
       "step": 150
+    },
+    {
+      "epoch": 0.05885598675740298,
+      "grad_norm": 0.8634781241416931,
+      "learning_rate": 0.00017279364993403443,
+      "loss": 1.5365,
+      "step": 160
+    },
+    {
+      "epoch": 0.06253448592974066,
+      "grad_norm": 0.8469012975692749,
+      "learning_rate": 0.00016774762593906525,
+      "loss": 1.532,
+      "step": 170
+    },
+    {
+      "epoch": 0.06621298510207835,
+      "grad_norm": 0.8828918933868408,
+      "learning_rate": 0.00016237397827022866,
+      "loss": 1.3797,
+      "step": 180
+    },
+    {
+      "epoch": 0.06989148427441604,
+      "grad_norm": 0.946323037147522,
+      "learning_rate": 0.00015669888679881007,
+      "loss": 1.3311,
+      "step": 190
+    },
+    {
+      "epoch": 0.07356998344675372,
+      "grad_norm": 1.0333322286605835,
+      "learning_rate": 0.00015075,
+      "loss": 1.2819,
+      "step": 200
+    },
+    {
+      "epoch": 0.07356998344675372,
+      "eval_loss": 1.464486837387085,
+      "eval_runtime": 65.2426,
+      "eval_samples_per_second": 17.55,
+      "eval_steps_per_second": 4.399,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6660412850176e+16,
+  "total_flos": 3.5547217133568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null